ImgAlign 4.1

Added in Automatic quality stepper to minimize artifacts, log file of outputs with possible artifacting, and the option to specify output folder

ImgAlign 4.0

Added RAFT optical flow neural network to further improve alignment results. Torch with CUDA is recommended for best performance if your GPU supports it, and must be installed from https://pytorch.org/get-started/locally/
Install as you would any other python package with the command:
pip install ImgAlign

ImgAlign 3.1

Added semi-automatic points, shaped points to help distinguish matching pairs, and post alignment color matching.

ImgAlign 3.0

Many new features such as manual point selection and thin plate spline warping.

ImgAlign

Now supports full homography mapping (warping), use option -f or --full to enable.
Better alignment algorithm implemented for more accurate matching.
4x scale now much more reliable.
Batch processing now does not halt when a match isn't found.
Generates a log file for failed matches.